A compact generative neural network can be distilled from a teacher generative neural network using a training network. The compact network can be trained on the input data and output data of the teacher network. The training network train the student network using a discrimination layer and one or more types of losses, such as perception loss and adversarial loss.
Legal claims defining the scope of protection, as filed with the USPTO.
5. The system of claim 1, wherein the neural network is one of a plurality of neural networks, and wherein one of the plurality of neural networks is trained to apply the effect for each object of a plurality of objects, the plurality of objects comprising the object.
7. The system of claim 6, wherein the plurality of neural networks are trained using a discriminative neural network that evaluates data output by the plurality of neural networks compared with target data.
8. The system of claim 5 wherein the system is a mobile device, and wherein the plurality of neural networks are stored on the mobile device.
12. The system of claim 1, wherein the effect is at least one of a painting style transfer, an aging style transfer, a wrinkle remover, a youth style transfer, or an aging style transfer.
13. The system of claim 1, wherein the object is at least one of teeth, a car, or an apple.
14. The system of claim 1, wherein the default losses comprise: a perception loss, an adversarial loss, and a high-frequency loss.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
June 22, 2023
December 31, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.